A novel learning algorithm for global synchronization of oscillatory neural networks

We present a cellular type oscillatory neural network for temporal pattern segmentation. The model comprises an array of locally connected neural oscillators with connections limited to a 4-connected neighborhood. By means of a novel learning rule and an initialization scheme, global synchronization can be accomplished without incurring any erroneous synchrony among uncorrelated objects. Most importantly, we do not need any global connections to and from other neural oscillators. It is shown in the paper that global synchronization and desynchronization can be achieved by means of locally connected synapses